A framework for building agentic apps

nanoMuse: an open-source personal agent for every device you own — one agent with a name and a face that does things, keeps working while the app is closed, remembers you, and asks before anything …

Repository for the Human Disease Ontology.

Ontology for the description of human clinical features

Public repository for Agent Skills

(ACL 2026 Findings) Learning on the Job: An Experience-Driven, Self-Evolving Agent for Long-Horizon Tasks

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

[ECCV 2026] The official implementation of paper "PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion"

Official repo for the paper "PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis"

MUSE-Autoskill - A self-evolving LLM agent that builds, tests, and reuses reusable skills — getting smarter with every task.

A version of verl to support diverse tool use [TMLR 2026]

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

A parameter-efficient fine-tuning framework for adapting SAM to nuclei instance segmentation and classification.

Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling serv…

a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Train transformer language models with reinforcement learning.

Build, evaluate, and integrate long-term memory for self-evolving agents.

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

A Python library for efficient Bayesian modeling with deep learning

Omnipose: a high-precision solution for morphology-independent cell segmentation

Core Python Controller of the ORCA Hand

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Spatial-SAM: a spatially consistent, annotation-efficient framework that combines 3D SDF memory with SAM2 few-shot learning for high-precision segmentation of large-scale 3D electron microscopy data.

[ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

Toolkit for large-scale whole-slide image processing.

TorchCFM: a Conditional Flow Matching library

SoTo is a framework for test-time search in autoregressive (AR) image generation, decoupling AR priors, search algorithms, and verifiers for flexible composition via simple YAML configs.

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.